医学教育管理 ›› 2025, Vol. 11 ›› Issue (6): 689-695.doi: 10. 3969/j. issn. 2096-045X. 2025. 06. 011

• 临床教学 • 上一篇    下一篇

头颈 CT 血管成像人工智能辅助重建在医学影像技术专业实践教学中的应用

赵澄,郑冲,李瑞利,卢洁*   

  1. 首都医科大学宣武医院放射与核医学科,北京 10005
  • 收稿日期:2025-06-20 修回日期:2025-09-23 出版日期:2025-12-20 发布日期:2026-01-15
  • 通讯作者: 卢洁 E-mail:alfland@163.com
  • 基金资助:

    1.首都医科大学2022年教育教学改革研究重点课题项目(2022JYZ044);2.北京市住培质量提高项目(住培2023007、2024011)

Application of AI-assisted reconstruction in head and neck CT angiography in medicalimaging technology professional practice teaching

Zhao Cheng, Zheng Chong, Li Ruili, Lu Jie*   

  1. Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, Beijing100053, China
  • Received:2025-06-20 Revised:2025-09-23 Online:2025-12-20 Published:2026-01-15

摘要: 目的 探讨头颈 CT 血管成像(computed tomography angiography,CTA)人工智能(artificial intelligence,AI)辅助重建教学模式在提升医学影像技术专业学生 CT血管成像扫描及重建技术教学中的应用价值。方法 将 2022年 1月至2023年3月在首都医科大学宣武医院放射与核医学科实习的15名医学影像技术专业学生纳入对照组,采用传统规范化教学模式培训;将2024年1月至2025年3月在首都医科大学宣武医院放射与核医学科实习的17名医学影像技术专业学生纳入试验组,采用AI自学结合规范化教学模式。两组分别通过理论考核、实际扫描操作考核、血管重建技能考核及满意度调查评价教学效果。结果 总体上,试验组在理论考核、实际扫描操作考核及血管重建技能考核中得分均显著高于对照组(P<0. 001),且后处理重建时间低于对照组(P<0. 01)。在头颈血管定位、解剖结构识别、特定病变描述、狭窄程度评估、伪影识别分析、血管重建时间等后处理技能细化项目考核中,试验组各项得分也均高于对照组(P<0. 01)。同时,试验组学生满意度评分均显著高于对照组(96. 35±1. 17 vs. 81. 60±1. 50,P<0. 001),试验组学生反馈该教学模式在提升对头颈部血管的解剖认识、提升学习兴趣、提高学习效率、改善图像质量以及提高专业水平方面有一定助力。结论 AI辅助教学模式能够有效提升学生对头颈部CTA操作及血管重建技能的掌握,但不能取代传统教学方法,需两者有效结合,才能为医学影像技术专业教学实践提供有力支撑。

Abstract: Objective To explore the application value of the artificial intelligence (AI) -assisted reconstruction teachingmode in head and neck Computed angiography (CTA) in improving the teaching of CT angiography scanning andreconstruction techniques for students majoring in imaging technology. Methods A total of 15 medical imaging technologystudents who interned in tomography from January 2022 to March 2023 were included in the control group and trained usingtraditional teaching methods, while 17 medical imaging technology students who interned in tomography from January 2024to March 2025 were included in the experimental group and were first self-taught with AI and then received standardized teaching training. The teaching effects of the two groups were evaluated through theoretical tests, practical scanningoperation tests, vascular reconstruction skills tests, and satisfaction surveys. Results Overall, the experimental groupscored significantly higher than the control group in theoretical assessment, practical scanning operation, and vascular postprocessing reconstruction skills (P<0. 001), and the post-processing reconstruction time was shorter than that of the controlgroup (P<0. 01). In the detailed post-processing skill assessment items such as head and neck vessel localization,anatomical structure identification, specific lesion description, stenosis degree evaluation, artifact recognition and analysis,and vascular reconstruction time, the scores of the experimental group were also significantly higher than those of the controlgroup (P<0. 01). Meanwhile, the satisfaction score of the experimental group was significantly higher than that of thecontrol group (96. 35±1. 17 vs. 81. 60±1. 50, P<0. 001). Students in the experimental group also provided feedback thatthis teaching model was helpful in improving the anatomical understanding of blood uessels in the head and neck region,enhancing learning interest, improving learning efficiency, and enhancing professional skills. Conclusion The AI-assistedteaching mode can effectively enhance students' mastery of head and neck CTA operation and vascular reconstruction skills,but it cannot replace traditional teaching methods. Only by effective combination of the two can provide favorable supportfor the teaching practice of medical imaging technology.

中图分类号: